用变分方法提升LoRA微调，效果更好且计算开销低。
Improving LoRA with Variational Learning
- 采用IVON变分算法，无需复杂技巧即可实现
- 在30亿参数大模型上，准确率提升1.3%，校准误差降5.4%
- 适合追求高效高精度微调的研究者和工程落地
贝叶斯方法虽能改善LoRA微调的校准性，但对准确率提升有限，甚至可能下降，且增加计算开销并需额外技巧。本文引入一种新提出的变分算法IVON，发现其易于实现且计算成本与AdamW相当，结合简单的后验剪枝技术，可显著提升多项指标。我们在千亿级大模型（Llama与Qwen系列）上进行了广泛实验，远超现有IVON应用规模。例如，在一组常识推理任务上微调Llama-3.2-3B模型，相比AdamW，准确率提高1.3%，期望校准误差（ECE）降低5.4%，优于AdamW及近期贝叶斯方法如Laplace-LoRA和BLoB。结果表明，使用IVON的变分学习能有效改进LoRA微调。
原文摘要 · Abstract (English)
Bayesian methods have recently been used to improve LoRA finetuning and, although they improve calibration, their effect on other metrics (such as accuracy) is marginal and can sometimes even be detrimental. Moreover, Bayesian methods also increase computational overheads and require additional tricks for them to work well. Here, we fix these issues by using a recently proposed variational algorithm called IVON. We show that IVON is easy to implement and has similar costs to AdamW, and yet it can also drastically improve many metrics by using a simple posterior pruning technique. We present extensive results on billion-scale LLMs (Llama and Qwen series) going way beyond the scale of existing applications of IVON. For example, we finetune a Llama-3.2-3B model on a set of commonsense reasoning tasks and improve accuracy over AdamW by 1.3% and reduce ECE by 5.4%, outperforming AdamW and other recent Bayesian methods like Laplace-LoRA and BLoB. Overall, our results show that variational learning with IVON can effectively improve LoRA finetuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。